A Deep Learning Based Model for Driving Risk Assessment

Abstract

In this paper a novel multilayer model is proposed for assessing driving risk. Studying aggressive behavior via massive driving data is essential for protecting road traffic safety and reducing losses of human life and property in smart city context. In particular, identifying aggressive behavior and driving risk are multi-factors combined evaluation process, which must be processed with time and environment. For instance, improper time and environment may facilitate abnormal driving behavior. The proposed Dynamic Multilayer Model consists of identifying instant aggressive driving behavior that can be visited within specific time windows and calculating individual driving risk via Deep Neural Networks based classification algorithms. Validation results show that the proposed methods are particularly effective for identifying driving aggressiveness and risk level via real dataset of 2129 drivers' driving behavior.

Driver behavior model for healthy driving style using machine learning methods

“…In [9] the researchers proposed a multilayer model for assessing driving risk. The proposed Dynamic Multilayer Model consists of identifying instant aggressive driving behavior that can be visited within specific time windows and calculating individual driving risk using Deep Neural Networks based classification algorithms.…”

Machine learning for next‐generation intelligent transportation systems: A survey

“…In a search to automate features extraction and take advantage of hidden features as well, CNN was used to classify driving styles with smartphone 71 data and DL was exploited to model driving risk from OBD and GPS information. 114…”